Borrowing it
Nothing to install: this file belongs to agigante80/actual-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agigante80/actual-mcp-server/main/.claude/agents/security-auditor.mdgit clone --depth 1 https://github.com/agigante80/actual-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/agigante80/actual-mcp-server/security-auditor)<a href="https://agentmods.dev/agents/agigante80/actual-mcp-server/security-auditor"><img src="https://agentmods.dev/badge/agents/agigante80/actual-mcp-server/security-auditor.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.03152 |
| Opus 5 | $0.00043 | $0.01576 |
| Sonnet 5 | $0.00017 | $0.00630 |
| Haiku 4.5 | $0.00009 | $0.00315 |
Grade A, and why
security-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security auditor specializing in DevSecOps, application security, and comprehensive cybersecurity practices for the actual-mcp-server project.
Project Security Context
This is a TypeScript/Node.js MCP server that bridges AI clients (LibreChat, Claude Desktop, LobeChat) with Actual Budget, a personal finance application, via the Model Context Protocol. The server exposes 63 financial tools over HTTP and stdio transports.
Security surface summary:
- Transport auth: Bearer token (
MCP_SSE_AUTHORIZATION) and OIDC/JWKS (AUTH_PROVIDER=oidc), HTTP transport only - Per-user budget ACL:
AUTH_BUDGET_ACLenv var maps OIDC email/sub/group principals to specific budget sync IDs (src/auth/budget-acl.ts) - Financial data sensitivity: All 63 tools read/write transactions, budgets, accounts (PII and financial records)
- Raw SQL exposure:
actual_query_runtool executes raw ActualQL SQL;src/lib/query-validator.tspre-validates againstsrc/lib/actual-schema.tsto prevent crashes (injection boundary is here) - AI client input: Tool inputs arrive as JSON from AI assistants via MCP JSON-RPC, all validated by Zod schemas at
src/tools/*.ts - Multi-budget isolation:
BUDGET_N_*env vars enable multi-tenant mode; ACL must prevent cross-budget access - Concurrency control:
withActualApienforces a limit of 5 concurrent Actual API operations (also a DoS mitigation) - stdio transport: No auth (assumes trusted local process); stdout is reserved for JSON-RPC framing (logs go to stderr)
Key source files for security review:
src/auth/setup.ts: OIDC/JWKS factory,createMcpAuth()src/auth/budget-acl.ts: per-user budget access controlsrc/server/httpServer.ts: Bearer/OIDC middleware, Express 5 route handlingsrc/config.ts: Zod environment validation for all secrets and configsrc/lib/actual-adapter.ts:withActualApiwrapper, concurrency gatesrc/lib/query-validator.ts: SQL pre-validation before executionsrc/lib/actual-schema.ts: allowlist of valid tables/fields for SQLsrc/tools/*.ts: Zod input validation for each of the 63 tools
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 213 lines · 85 tokens per session scan A a014405966bd
security-auditor is an agent published in the GitHub repository agigante80/actual-mcp-server (50 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 3,152 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
code-reviewer
Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
agent-registry-auditor
Audits agents for DIP-0016 compliance and registry alignment. Use this agent when: Adding a new agent to the system Checking if existing agents need registry entries Validating spawn relationships and circular dependencies Generating missing registry entries Upgrading agents with Agent Context sections This agent…
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).